I have 5000 degraded pictures ( pixelated, blurry, too much luminosity ... ) and their clean versions, and I would like to train a model so that it can predict how to correct future pictures.

I've tried to get as much information as possible, and I think I'll have to train a deep learning model using Tensorflow & Keras, and I'll have to do image inpainting, more precisely a deconvolution method, to get to the expected result.

However, I have strictly no idea about how to get there. I would load both pictures using PIL Image, then convert it into a numpy array, but then I don't really know what to do next.

I do not have any code to show, however I can provide you with a couple pictures. Thanks a lot

  • $\begingroup$ any image to image or CAE-like network would work $\endgroup$ – mshlis Jan 18 at 23:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.